CN110309959A - A kind of emergency event processing method, system and storage medium - Google Patents
A kind of emergency event processing method, system and storage medium Download PDFInfo
- Publication number
- CN110309959A CN110309959A CN201910533681.0A CN201910533681A CN110309959A CN 110309959 A CN110309959 A CN 110309959A CN 201910533681 A CN201910533681 A CN 201910533681A CN 110309959 A CN110309959 A CN 110309959A
- Authority
- CN
- China
- Prior art keywords
- emergency event
- information
- disposition
- event
- response project
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 230000004044 response Effects 0.000 claims abstract description 98
- 230000000875 corresponding effect Effects 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 58
- 230000008569 process Effects 0.000 claims description 46
- 238000011156 evaluation Methods 0.000 claims description 44
- 230000008451 emotion Effects 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000013136 deep learning model Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 16
- 238000011160 research Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005111 flow chemistry technique Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to field of traffic control, a kind of emergency event processing method, system, storage medium, the problem for solving road emergency event disposal options confusion are provided.A kind of emergency event processing method provided by the invention, comprising: obtain emergency event, determine the property of emergency event;According to the property of emergency event, the Response project of the emergency event of corresponding properties is called;Disposition people is notified to be disposed emergency event according to Response project;Receive the feedback information of emergency event disposition situation, store feedback information to the information for receiving disposition completion.Emergency event can be focused on, arrange disposition unit to be disposed emergency event in time, while can receive feedback information, and then be adjusted optimization to Response project.
Description
Technical field
The present invention relates to field of traffic control, and in particular to a kind of emergency event processing method, system and storage medium.
Background technique
As road traffic sustained and rapid development, traffic administration pressure continue to increase, traffic accident quantity is also continuous
Soaring, harmfulness has seriously affected the sustainable development in China and the stabilization of society.How freeway traffic thing is improved
Therefore prevention and adaptibility to response, control and the serious social danger for reducing traffic accidents initiation, it is freeway traffic
The hot issue of safety and contingency management area research.China has also put into effect a series of laws and regulations for problems, existing
Stage China different regions and department have carried out certain research work in terms of emergency event quick response and decision support, but
The research for some explorations that be more be, not formed systematic theoretical system and application technology, also without proposing special needle
Theory, technology and the scheme of quick response and decision support to different type highway vital emergent event.
Domestic and international situation is taken a broad view of, the Emergent Public Events in China constantly occur to bring to the people's lives and property very big
Loss, therefore the research of public emergency also becomes an academic hot spot.Many scholars study burst thing from different perspectives
The key problems such as the origin cause of formation, type, the prevention of part.Emergency response system, emergency commading system are various contingency theories, the reality of technology
It tramples, therefore, more and more focus of attention emergency response systems, emergency commading system also achieve part research achievement.But
It was found that few to the research of mobile terminal emergency commading system, existing research is nor very thorough.
Especially, be all according to the preset Response project of emergency event it is rigid, the improvement obtained in the application can not and
When effectively update in prediction scheme storehouse and the staff for relying on command centre is called in the optimization of prediction scheme, need more work
Make the support of experience, easily because caused by flow of personnel event handling it is chaotic, generate undesirable social influence.
Summary of the invention
Present invention solves the technical problem that being the problem of road emergency event disposal options confusion, a kind of emergency event is provided
Processing method, system, storage medium.
In order to solve the above technical problem, the present invention provides technical solution are as follows:
A kind of emergency event processing method, comprising: obtain emergency event, determine the property of emergency event;According to emergency event
Property calls the Response project of the emergency event of corresponding properties;According to Response project notify disposition people to emergency event at
It sets;Receive the feedback information of emergency event disposition situation, store feedback information to the information for receiving disposition completion.
The Response project that event is called according to event property notifies disposition unit to be disposed according to Response project;Disposition
In the process, feedback information is received, and feedback information is stored.
Emergency event can be focused on, arrange disposition unit to be disposed emergency event in time, while can
To receive feedback information, and then optimization is adjusted to Response project.
Preferably, further includes: during the feedback information for receiving emergency event disposition situation, if receiving burst
The information of event property mistake redefines the property of emergency event, calls the Response project of the emergency event of corresponding properties.Thing
The determination of part property is not staff's determination at the scene, but carries out identification or command centre according to video image
The judgement that is carried out in distal end of personnel, therefore property determinations may be wrong, so cause the prediction scheme transferred be it is wrong, because
This, needs to transfer prediction scheme again.
Preferably, the feedback information is the writing record of picture, disposal process.The feedback information work live by disposition
Personnel upload to cloud.
Preferably, the writing record of the disposal process is each step in the disposal process according to documented by Response project
Practical operation information and disposition object reaction.Detailed record carried out to disposal process, it is convenient afterwards to Response project into
Row adjusting and optimizing.
Preferably, after the information for receiving disposition completion, accident handling evaluation opinion is obtained, according to event handling opinion
Optimize prediction scheme.The disposition opinion and disposition evaluation opinion that disposal personnel is collected after the completion of event handling, carry out Response project excellent
Change.
Preferably, optimize the method for prediction scheme according to event handling opinion are as follows: using event handling evaluation opinion as attribute feelings
Feel label, the data set that the writing record of automatic marking accident handling is formed;Google is used on automatic marking data set
Skip-gram model training in word2vec frame obtains the semantic term vector dictionary of tradition of pre-training;By tabling look-up, by thing
Word in the sentence of the writing record of part disposition is initialized as term vector;Using deep learning model ASWV by accident handling opinion
In the attribute emotion information that contains be dissolved into the training process of term vector: language is contained using the training of traditional neural network language model
The term vector of adopted information indicates;It is indicated using the term vector that deep learning model learning contains attribute emotion information;Fusion is semantic
Information and attribute emotion information, training deep learning model ASWV, obtain attribute emotion term vector;Check iteration stopping condition,
If meeting condition, output attribute emotion term vector;Output attribute emotion term vector, using attribute emotion term vector as depth mind
Input layer building sentiment analysis system through network model carries out sentiment analysis to Response project.According to evaluation opinion to accident at
The writing record for setting prediction scheme is handled, and then obtains the input vector based on the record of Response project flow processing, is obtained
The evaluation to Response project in event handling is taken, and then prediction scheme is adjusted according to evaluation;Response project is denumerable, and
The data of the record of emergency event and disposal process are magnanimity, the application by artificial mode to emergency event Response project
It is more difficult that effect, which carries out evaluation,.
Preferably, the method that sentiment analysis is carried out to Response project are as follows: Response project information is pre-processed, is wrapped
Include subordinate sentence, gradation, part-of-speech tagging;Feature extraction is carried out to pretreated text information, by text information vectorization;By vector
Emotion tendency judgement is carried out in the text information input sentiment analysis system of change.It is in sentiment analysis system, event handling is pre-
Writing record in case application process is established with final evaluation information to be contacted, and each step has correspondence in Response project
Writing record, therefore Response project also contact with evaluation information foundation, and then can be analyzed Response project, and judgement is newly
Whether the Response project of design or original Response project can obtain preferable evaluation.
A kind of critical events dealing system, including cloud, the cloud include that obtain module, event property true for emergency event
Cover half block, Response project calling module, disposition task allocating module, feedback information receiving module, memory module;The burst thing
Part obtains module and obtains emergency event, and the event property determining module determines the property of emergency event;According to emergency event
Property, the Response project calling module call the Response project of the emergency event of corresponding properties;The disposition task distributes mould
Root tuber notifies disposition people to be disposed emergency event according to Response project;The feedback information receiving module receives at emergency event
Set the feedback information of situation, store feedback information to the information for receiving disposition completion, the memory module store feedback information.It can
To focus on to emergency event, disposition unit is arranged to be disposed emergency event in time, while can receive feedback
Information, and then optimization is adjusted to Response project.
It preferably, further include site disposal end, the site disposal end includes disposal process logging modle, communication module,
The disposal process logging modle obtains the writing record of disposal process, and the writing record of the disposal process is pre- according to disposition
The reaction of the practical operation information of each step and disposition object in disposal process documented by case.Disposal process carries out detailed
Record, it is convenient that optimization is adjusted to Response project afterwards.
A kind of storage medium of emergency event processing, is stored with the program that can be performed above-mentioned method.
Compared with prior art, the device have the advantages that are as follows: emergency event can be focused on, in time
It arranges disposition unit to be disposed emergency event, while can receive feedback information, and then be adjusted to Response project excellent
Change;It handles, and then is obtained with the note of Response project flow processing according to writing record of the evaluation opinion to accident handling prediction scheme
Input vector based on record obtains the evaluation to Response project in event handling, and then is adjusted according to evaluation to prediction scheme
It is whole;Response project is denumerable, and the data of the record of emergency event and disposal process are magnanimity, passes through artificial mode pair
It is more difficult that the application effect of emergency event Response project, which carries out evaluation, thus by deep learning come to Response project into
Row optimization is the important method for improving emergency event treatment effeciency.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of emergency event processing method.
Fig. 2 is a kind of another flow diagram of emergency event processing method.
Fig. 3 is a kind of another flow diagram of emergency event processing method.
Fig. 4 is a kind of schematic diagram of critical events dealing system.
Fig. 5 is a kind of another schematic diagram of critical events dealing system.
Specific embodiment
It the following examples are further illustrations of the invention, is not limitation of the present invention.
Embodiment 1
A kind of emergency event processing method, in some embodiments of the present application, as shown in Figure 1, comprising: emergency event is obtained,
Determine the property of emergency event;According to the property of emergency event, the Response project of the emergency event of corresponding properties is called;According to place
Prediction scheme notice disposition people is set to be disposed emergency event;The feedback information for receiving emergency event disposition situation, stores feedback letter
It ceases to the information for receiving disposition completion.
The Response project that event is called according to event property notifies disposition unit to be disposed according to Response project;Disposition
In the process, feedback information is received, and feedback information is stored.
Emergency event can be focused on, arrange disposition unit to be disposed emergency event in time, while can
To receive feedback information, and then optimization is adjusted to Response project.
In some embodiments of the present application, further includes: the mistake of the feedback information for receiving emergency event disposition situation
Cheng Zhong redefines the property of emergency event if receiving the information of emergency event property mistake, calls the burst of corresponding properties
The Response project of event.
The determination of event property is not what staff at the scene determined, but according to video image carry out identification or
The judgement that the personnel of person command centre carry out in distal end, therefore property determination may be mistake, and then lead to the prediction scheme transferred
Be it is wrong, therefore, it is necessary to transfer prediction scheme again.
In some embodiments of the present application, the feedback information is the writing record of picture, disposal process.
Feedback information uploads to cloud by the staff at disposition scene.
In some embodiments of the present application, the writing record of the disposal process is according to documented by Response project
Set the practical operation information of each step in process and the reaction of disposition object.
Detailed record is carried out to disposal process, it is convenient that optimization is adjusted to Response project afterwards.
In some embodiments of the present application, after the information for receiving disposition completion, accident handling evaluation opinion is obtained,
Optimize prediction scheme according to event handling opinion.
The disposition opinion and disposition evaluation opinion that disposal personnel is collected after the completion of event handling, carry out Response project excellent
Change.
In some embodiments of the present application, as shown in Fig. 2, determining the property of emergency event after obtaining emergency event, adjust
With the Response project of the emergency event of corresponding properties, the feedback information of emergency event disposition situation is received, if receiving emergency event
The feedback information for disposing situation, redefines the property of event;If not receiving the feedback information of emergency event disposition situation, obtain
Accident handling evaluation opinion optimizes prediction scheme according to event handling opinion.
In some embodiments of the present application, optimize the method for prediction scheme according to event handling opinion are as follows: comment event handling
The data set that valence opinion is formed as attribute affective tag, the writing record of automatic marking accident handling;In automatic marking data
The semantic term vector dictionary of the tradition that pre-training is obtained using the Skip-gram model training in Google word2vec frame on collection;
By tabling look-up, the word in the sentence of the writing record of event handling is initialized as term vector;Using deep learning model ASWV
The attribute emotion information contained in accident handling opinion is dissolved into the training process of term vector: using traditional neural network language
The term vector that model training contains semantic information indicates;Contain the term vector of attribute emotion information using deep learning model learning
It indicates;Semantic information and attribute emotion information are merged, training deep learning model ASWV obtains attribute emotion term vector;It checks
Iteration stopping condition, if meeting condition, output attribute emotion term vector;Output attribute emotion term vector, by attribute emotion word
Vector carries out sentiment analysis to Response project as the input layer building sentiment analysis system of deep neural network model.
It is handled, and then is obtained at Response project process according to writing record of the evaluation opinion to accident handling prediction scheme
Input vector based on the record of reason obtains the evaluation to Response project in event handling, and then according to evaluation to prediction scheme
It is adjusted;Response project is denumerable, and the data of the record of emergency event and disposal process are magnanimity, by artificial
It is more difficult that mode, which carries out evaluation to the application effect of emergency event Response project,.
In some embodiments of the present application, the method that sentiment analysis is carried out to Response project are as follows: to Response project
Information is pre-processed, including subordinate sentence, gradation, part-of-speech tagging;Feature extraction is carried out to pretreated text information, by text
Information vector;Emotion tendency judgement will be carried out in the text information input sentiment analysis system of vectorization.
In sentiment analysis system, the writing record in event handling prediction scheme application process is established with final evaluation information
Connection, and each step has corresponding writing record in Response project, therefore Response project is also established with evaluation information and joined
System, and then can analyze Response project, judge whether newly-designed Response project or original Response project can be with
Obtain preferable evaluation.
In some embodiments of the present application, as shown in figure 3, determining the property of emergency event after obtaining emergency event, adjust
With the Response project of the emergency event of corresponding properties, the feedback information of emergency event disposition situation is received, if receiving emergency event
The feedback information for disposing situation, redefines the property of event;If not receiving the feedback information of emergency event disposition situation, obtain
Accident handling evaluation opinion optimizes prediction scheme according to event handling opinion.Optimize the method for prediction scheme according to event handling opinion are as follows: will
The data set that event handling evaluation opinion is formed as attribute affective tag, the writing record of automatic marking accident handling;Certainly
The semantic word of the tradition that pre-training is obtained using the Skip-gram model training in Google word2vec frame on dynamic labeled data collection
Vector dictionary;By tabling look-up, the word in the sentence of the writing record of event handling is initialized as term vector.Using traditional neural
The term vector that netspeak model training contains semantic information indicates;Attribute emotion information is contained using deep learning model learning
Term vector indicate;Merge semantic information and attribute emotion information, training deep learning model ASWV, obtain attribute emotion word to
Amount;Check iteration stopping condition, if meeting condition, output attribute emotion term vector;Output attribute emotion term vector, by attribute
Input layer building sentiment analysis system of the emotion term vector as deep neural network model.Response project information is located in advance
Reason, including subordinate sentence, gradation, part-of-speech tagging;Feature extraction is carried out to pretreated text information, by text information vectorization;
Emotion tendency judgement will be carried out in the text information input sentiment analysis system of vectorization.
A kind of system of emergency event processing, in some embodiments of the present application, as shown in figure 4, include cloud, it is described
Cloud include emergency event obtain module, event property determining module, Response project calling module, disposition task allocating module,
Feedback information receiving module, memory module;The emergency event obtains module and obtains emergency event, and the event property determines mould
Block determines the property of emergency event;According to the property of emergency event, the Response project calling module calls the prominent of corresponding properties
The Response project of hair event;The disposition task allocating module according to Response project notify disposition people to emergency event at
It sets;The feedback information receiving module receives the feedback information of emergency event disposition situation, and store feedback information is to receiving disposition
The information of completion, the memory module store feedback information.
Emergency event can be focused on, arrange disposition unit to be disposed emergency event in time, while can
To receive feedback information, and then optimization is adjusted to Response project.
In some embodiments of the present application, the feedback information receiving module receives the feedback of emergency event disposition situation
During information, if receiving the information of emergency event property mistake, the property of emergency event is redefined, calls correspondence
The Response project of the emergency event of matter.
The determination of event property is not what staff at the scene determined, but according to video image carry out identification or
The judgement that the personnel of person command centre carry out in distal end, therefore property determination may be mistake, and then lead to the prediction scheme transferred
Be it is wrong, therefore, it is necessary to transfer prediction scheme again.
In some embodiments of the present application, the feedback information is the writing record of picture, disposal process.
Feedback information uploads to cloud by the staff at disposition scene.
It further include site disposal end in some embodiments of the present application, the site disposal end includes disposal process note
Module, communication module are recorded, the disposal process logging modle obtains the writing record of disposal process, the text of the disposal process
It is recorded as the practical operation information of each step in the disposal process according to documented by Response project and the reaction of disposition object.
Disposal process carries out detailed record, convenient to be adjusted optimization to Response project afterwards.
It further include evaluation opinion receiving module, prediction scheme optimization module, the evaluation meaning in some embodiments of the present application
After seeing that receiving module receives the information that disposition is completed, accident handling evaluation opinion is obtained, the prediction scheme optimization module is according to event
It disposes evaluation opinion and optimizes prediction scheme.
The disposition opinion and disposition evaluation opinion that disposal personnel is collected after the completion of event handling, carry out Response project excellent
Change.
In other embodiments of the application, determined as shown in figure 5, the emergency event obtains module with event property
Module connection, the event property determining module are connected with Response project calling module, and the Response project calling module exists together
Task allocating module connection is set, the disposition task allocating module is connected with feedback information receiving module, and the feedback information connects
It receives module to connect with event property determining module and memory module, the memory module is connected with evaluation opinion receiving module, institute
Evaluation opinion receiving module is stated with former optimization module connection.The member optimization module is connected with prediction scheme preprocessing module.It is described existing
The disposal process logging modle at field disposition end is connected by communication module with memory module.
In some embodiments of the present application, the function of the optimization module are as follows: prediction scheme is optimized according to event handling opinion
Method are as follows: using event handling evaluation opinion as attribute affective tag, what the writing record of automatic marking accident handling was formed
Data set;Pre-training is obtained using the Skip-gram model training in Google word2vec frame on automatic marking data set
The semantic term vector dictionary of tradition;By tabling look-up, the word in the sentence of the writing record of event handling is initialized as term vector;
The attribute emotion information contained in accident handling opinion is dissolved into the training process of term vector using deep learning model ASWV:
It is indicated using the term vector that semantic information is contained in the training of traditional neural network language model;Contained using deep learning model learning
The term vector of attribute emotion information indicates;Semantic information and attribute emotion information are merged, training deep learning model ASWV is obtained
Obtain attribute emotion term vector;Check iteration stopping condition, if meeting condition, output attribute emotion term vector;Output attribute feelings
Feel term vector, it is pre- to disposing using attribute emotion term vector as the input layer building sentiment analysis system of deep neural network model
Case carries out sentiment analysis.
It is handled, and then is obtained at Response project process according to writing record of the evaluation opinion to accident handling prediction scheme
Input vector based on the record of reason obtains the evaluation to Response project in event handling, and then according to evaluation to prediction scheme
It is adjusted;Response project is denumerable, and the data of the record of emergency event and disposal process are magnanimity, by artificial
It is more difficult that mode, which carries out evaluation to the application effect of emergency event Response project,.
In some embodiments of the present application, the prediction scheme optimization module is connected with prediction scheme preprocessing module, the prediction scheme
Preprocessing module carries out sentiment analysis after handling prediction scheme: pre-processing to Response project information, including subordinate sentence, gradation, word
Property mark;Feature extraction is carried out to pretreated text information, by text information vectorization;The text information of vectorization is defeated
Enter progress emotion tendency judgement in sentiment analysis system.
In sentiment analysis system, the writing record in event handling prediction scheme application process is established with final evaluation information
Connection, and each step has corresponding writing record in Response project, therefore Response project is also established with evaluation information and joined
System, and then can analyze Response project, judge whether newly-designed Response project or original Response project can be with
Obtain preferable evaluation.Evaluation information is generally divided into very satisfied, satisfied, general, dissatisfied.
Above-listed detailed description is illustrating for possible embodiments of the present invention, and above embodiments are not to limit this
The scope of the patents of invention, all equivalence enforcements or change without departing from carried out by the present invention, is intended to be limited solely by the scope of the patents of this case.
Claims (10)
1. a kind of emergency event processing method characterized by comprising obtain emergency event, determine the property of emergency event;
According to the property of emergency event, the Response project of the emergency event of corresponding properties is called;Disposition people couple is notified according to Response project
Emergency event is disposed;Receive emergency event disposition situation feedback information, store feedback information to receive disposition complete
Information.
2. a kind of emergency event processing method according to claim 1, which is characterized in that further include: the reception burst
During the feedback information of event handling situation, if receiving the information of emergency event property mistake, burst thing is redefined
The property of part calls the Response project of the emergency event of corresponding properties.
3. a kind of emergency event processing method according to claim 1, which is characterized in that the feedback information be picture,
The writing record of disposal process.
4. a kind of emergency event processing method according to claim 1, which is characterized in that the text of the disposal process is remembered
Record is the reaction of the practical operation information of each step and disposition object in the disposal process according to documented by Response project.
5. a kind of emergency event processing method according to claim 1, which is characterized in that the letter for receiving disposition and completing
After breath, accident handling evaluation opinion is obtained, prediction scheme is optimized according to event handling opinion.
6. a kind of emergency event processing method according to claim 1, which is characterized in that optimized according to event handling opinion
The method of prediction scheme are as follows: using event handling evaluation opinion as attribute affective tag, the writing record shape of automatic marking accident handling
At data set;The Skip-gram model training in Google word2vec frame is used to obtain on automatic marking data set pre-
The semantic term vector dictionary of trained tradition;By tabling look-up, the word in the sentence of the writing record of event handling is initialized as word
Vector;The attribute emotion information contained in accident handling opinion is dissolved into the training of term vector using deep learning model ASWV
Process: it is indicated using the term vector that semantic information is contained in the training of traditional neural network language model;Using deep learning model
Practise the term vector expression for containing attribute emotion information;Merge semantic information and attribute emotion information, training deep learning model
ASWV obtains attribute emotion term vector;Check iteration stopping condition, if meeting condition, output attribute emotion term vector;Output
Attribute emotion term vector, using attribute emotion term vector as the input layer building sentiment analysis system pair of deep neural network model
Response project carries out sentiment analysis.
7. a kind of emergency event processing method according to claim 6, which is characterized in that described to carry out feelings to Response project
Feel the method for analysis are as follows: pre-process to Response project information, including subordinate sentence, gradation, part-of-speech tagging;To pretreated text
This information carries out feature extraction, by text information vectorization;It will be carried out in the text information input sentiment analysis system of vectorization
Emotion tendency judgement.
8. a kind of critical events dealing system, which is characterized in that including cloud, the cloud include emergency event obtain module,
Event property determining module, Response project calling module, disposition task allocating module, feedback information receiving module, memory module;
The emergency event obtains module and obtains emergency event, and the event property determining module determines the property of emergency event;According to
The property of emergency event, the Response project calling module call the Response project of the emergency event of corresponding properties;The disposition
Task allocating module notifies disposition people to be disposed emergency event according to Response project;The feedback information receiving module receives
The feedback information of situation, store feedback information to the information for receiving disposition completion, the memory module storage are disposed in emergency event
Feedback information.
9. a kind of critical events dealing system according to claim 8, which is characterized in that further include site disposal end, institute
Stating site disposal end includes disposal process logging modle, communication module, and the disposal process logging modle obtains disposal process
Writing record, the writing record of the disposal process are the reality of each step in the disposal process according to documented by Response project
The reaction of operation information and disposition object.
10. a kind of storage medium of emergency event processing, which is characterized in that any one of claim 1 ~ 7 can be performed by being stored with
The program of the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910533681.0A CN110309959A (en) | 2019-06-19 | 2019-06-19 | A kind of emergency event processing method, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910533681.0A CN110309959A (en) | 2019-06-19 | 2019-06-19 | A kind of emergency event processing method, system and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110309959A true CN110309959A (en) | 2019-10-08 |
Family
ID=68076528
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910533681.0A Pending CN110309959A (en) | 2019-06-19 | 2019-06-19 | A kind of emergency event processing method, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110309959A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111612422A (en) * | 2020-05-21 | 2020-09-01 | 北京软通智慧城市科技有限公司 | Method and device for responding to emergency, storage medium and equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102594783A (en) * | 2011-01-14 | 2012-07-18 | 中国科学院软件研究所 | Network security emergency responding method |
CN103207855A (en) * | 2013-04-12 | 2013-07-17 | 广东工业大学 | Fine-grained sentiment analysis system and method specific to product comment information |
CN105741218A (en) * | 2016-03-04 | 2016-07-06 | 公安部道路交通安全研究中心 | Emergency plan generation server, method, system and client |
CN107066445A (en) * | 2017-04-11 | 2017-08-18 | 华东师范大学 | The deep learning method of one attribute emotion word vector |
CN107527153A (en) * | 2017-08-31 | 2017-12-29 | 东莞中国科学院云计算产业技术创新与育成中心 | Emergencies in public safety plan for emergency handling generation method and device |
-
2019
- 2019-06-19 CN CN201910533681.0A patent/CN110309959A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102594783A (en) * | 2011-01-14 | 2012-07-18 | 中国科学院软件研究所 | Network security emergency responding method |
CN103207855A (en) * | 2013-04-12 | 2013-07-17 | 广东工业大学 | Fine-grained sentiment analysis system and method specific to product comment information |
CN105741218A (en) * | 2016-03-04 | 2016-07-06 | 公安部道路交通安全研究中心 | Emergency plan generation server, method, system and client |
CN107066445A (en) * | 2017-04-11 | 2017-08-18 | 华东师范大学 | The deep learning method of one attribute emotion word vector |
CN107527153A (en) * | 2017-08-31 | 2017-12-29 | 东莞中国科学院云计算产业技术创新与育成中心 | Emergencies in public safety plan for emergency handling generation method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111612422A (en) * | 2020-05-21 | 2020-09-01 | 北京软通智慧城市科技有限公司 | Method and device for responding to emergency, storage medium and equipment |
CN111612422B (en) * | 2020-05-21 | 2023-08-11 | 北京软通智慧科技有限公司 | Emergency response method, device, storage medium and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111259873B (en) | Table data extraction method and device | |
CN110674295A (en) | Data labeling system based on deep learning | |
CN103886080B (en) | Method for extracting road traffic information from Internet unstructured text | |
CN114004210A (en) | Emergency plan generating method, system, equipment and medium based on neural network | |
CN106066849A (en) | A kind of template page editing system and method | |
CN113868419B (en) | Text classification method, device, equipment and medium based on artificial intelligence | |
CN111949779A (en) | Intelligent rail transit response method and system based on knowledge graph | |
CN111860653A (en) | Visual question answering method and device, electronic equipment and storage medium | |
CN112036129A (en) | Power distribution network emergency drilling scheme digital aided design system and method | |
CN114819004A (en) | Violation identification method and system based on multi-source data fusion | |
CN109299470A (en) | The abstracting method and system of trigger word in textual announcement | |
CN112395887A (en) | Dialogue response method, dialogue response device, computer equipment and storage medium | |
CN110309959A (en) | A kind of emergency event processing method, system and storage medium | |
CN116881395A (en) | Public opinion information detection method and device | |
CN109213520A (en) | A kind of annotation point recommended method and system based on Recognition with Recurrent Neural Network | |
CN114971530A (en) | Natural language processing-based collaborative operation and maintenance method and device | |
CN117726826A (en) | News report-oriented multi-scene AI aided manuscript writing method | |
CN117275466A (en) | Business intention recognition method, device, equipment and storage medium thereof | |
CN111062207A (en) | Expression image processing method and device, computer storage medium and electronic equipment | |
KR102470959B1 (en) | Construction Site Management System and Management Method Based on Technologies for Automatic Intent Recognition and Photo Messaging with Construction Photographs | |
CN113824722A (en) | Network security dynamic early warning system based on knowledge graph | |
Zaguia et al. | Using multimodal fusion in accessing web services | |
CN111832651A (en) | Video multi-mode emotion inference method and device | |
CN112287104A (en) | Natural language processing method and device | |
CN111209729A (en) | Method and device for identifying financial subject calculation relationship based on sequence labeling |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191008 |
|
RJ01 | Rejection of invention patent application after publication |